{"url":"/dataset/ppi","name":"PPI","full_name":"Protein-Protein Interactions (PPI)","description_markdown":"protein roles—in terms of their cellular functions from\r\ngene ontology—in various protein-protein interaction (PPI) graphs, with each graph corresponding\r\nto a different human tissue [41]. positional gene sets are used, motif gene sets and immunological\r\nsignatures as features and gene ontology sets as labels (121 in total), collected from the Molecular\r\nSignatures Database [34]. The average graph contains 2373 nodes, with an average degree of 28.8.","description_withheld":null,"homepage":"http://snap.stanford.edu/graphsage/#datasets","introduced_date":"2017-06-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/inductive-representation-learning-on-large","title":"Inductive Representation Learning on Large Graphs","first_author":"William L. Hamilton","url":null},"license":null,"modalities":[],"tasks":[{"name":"Node Classification","url":"/task/node-classification","datasets_with_task":"/datasets/task/node-classification"},{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"}],"languages":[],"variants":["PPI"],"data_loaders":[{"repo":"https://github.com/rusty1s/pytorch_geometric","url":"https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html","frameworks":["pytorch"]},{"repo":"https://github.com/dmlc/dgl","url":"https://docs.dgl.ai/api/python/dgl.data.html#dgl.data.PPIDataset","frameworks":["pytorch","tf","mxnet"]},{"repo":"https://github.com/danielegrattarola/spektral","url":"https://graphneural.network/datasets/#ppi","frameworks":["tf"]}],"num_papers_in_archive":309,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/node-classification-on-ppi","task":"Node Classification","dataset_variant":"PPI","rows":24,"metrics":["F1","Micro-F1","Micro F1","Macro-F1"],"first_row_in_archive_order":{"model":"g2-MLP","paper":"/paper/a-proposal-of-multi-layer-perceptron-with","metrics":{"F1":"99.71"},"code_links":[{"title":"nnaakkaaii/g2-MLP","url":"https://github.com/nnaakkaaii/g2-MLP"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/link-prediction-on-ppi","task":"Link Prediction","dataset_variant":"PPI","rows":2,"metrics":["AP","AUC","Accuracy"],"first_row_in_archive_order":{"model":"PPPNE","paper":"/paper/pppne-personalized-proximity-preserved","metrics":{"AP":"84.1%","AUC":"82.7%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/the-split-matters-flat-minima-methods-for","title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs","date":"2023-06-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-proposal-of-multi-layer-perceptron-with","title":"A Proposal of Multi-Layer Perceptron with Graph Gating Unit for Graph Representation Learning and its Application to Surrogate Model for FEM","date":"2022-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graph-representation-learning-beyond-node-and","title":"Graph Representation Learning Beyond Node and Homophily","date":"2022-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pppne-personalized-proximity-preserved","title":"PPPNE: Personalized proximity preserved network embedding","date":"2022-02-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vq-gnn-a-universal-framework-to-scale-up","title":"VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization","date":"2021-10-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/simple-and-deep-graph-convolutional-networks-1","title":"Simple and Deep Graph Convolutional Networks","date":"2020-07-04","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-graph-contrastive-representation","title":"Deep Graph Contrastive Representation Learning","date":"2020-06-07","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sign-scalable-inception-graph-neural-networks","title":"SIGN: Scalable Inception Graph Neural Networks","date":"2020-04-23","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bridging-the-gap-between-spectral-and-spatial","title":"Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks","date":"2020-03-26","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/sgas-sequential-greedy-architecture-search","title":"SGAS: Sequential Greedy Architecture Search","date":"2019-11-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hyperbolic-graph-convolutional-neural","title":"Hyperbolic Graph Convolutional Neural Networks","date":"2019-10-28","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deepgcns-making-gcns-go-as-deep-as-cnns","title":"DeepGCNs: Making GCNs Go as Deep as CNNs","date":"2019-10-15","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/graphsaint-graph-sampling-based-inductive","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","date":"2019-07-10","rows_on_this_dataset":1,"code_links":8,"syntology":null},{"paper":"/paper/graph-star-net-for-generalized-multi-task-1","title":"Graph Star Net for Generalized Multi-Task Learning","date":"2019-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cluster-gcn-an-efficient-algorithm-for","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","date":"2019-05-20","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/graphnas-graph-neural-architecture-search","title":"GraphNAS: Graph Neural Architecture Search with Reinforcement Learning","date":"2019-04-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/large-scale-learnable-graph-convolutional","title":"Large-Scale Learnable Graph Convolutional Networks","date":"2018-08-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/representation-learning-on-graphs-with","title":"Representation Learning on Graphs with Jumping Knowledge Networks","date":"2018-06-09","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gaan-gated-attention-networks-for-learning-on","title":"GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs","date":"2018-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","rows_on_this_dataset":1,"code_links":93,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":106,"samples_ran":50,"samples_unverified":56,"pointer_only_for_licence":43,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/inductive-representation-learning-on-large","title":"Inductive Representation Learning on Large Graphs","date":"2017-06-07","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/node2vec-scalable-feature-learning-for","title":"node2vec: Scalable Feature Learning for Networks","date":"2016-07-03","rows_on_this_dataset":2,"code_links":20,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":25,"samples_ran":8,"samples_unverified":17,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":12,"samples_harvested":185,"samples_ran":74,"samples_unverified":111,"pointer_only_for_licence":60,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}